{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6YMTT3XCRAXU6DU5XJEKOSWICD","short_pith_number":"pith:6YMTT3XC","schema_version":"1.0","canonical_sha256":"f61939eee2882f4f0e9dba48a74ac810e63f21c7a760eae302d91e0b51cab6cb","source":{"kind":"arxiv","id":"1511.02680","version":2},"attestation_state":"computed","paper":{"title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Alex Kendall, Roberto Cipolla, Vijay Badrinarayanan","submitted_at":"2015-11-09T14:00:21Z","abstract_excerpt":"We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making. Our contribution is a practical system which is able to predict pixel-wise class labels with a measure of model uncertainty. We achieve this by Monte Carlo sampling with dropout at test time to generate a posterior distribution of pixel class labels. In addition, we show that modelling uncertainty improves segmentation performance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1511.02680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:00:21Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"6393eb3a605c67d4a10f91f1f5429a73da7bf0b81afab862187a1457f711f620","abstract_canon_sha256":"8fce2cde37afe7188628c36a193d1d6c6de124396db7b44f753ebc8e676d348e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:49.852512Z","signature_b64":"1sgeucsBUez9UK+2DrPCZ3FIc5QBBXydiorpwg8EXbhnsoUo4EFeXQ391QeCsukCYaZX4gH4qE1uUJK8XC3cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61939eee2882f4f0e9dba48a74ac810e63f21c7a760eae302d91e0b51cab6cb","last_reissued_at":"2026-05-18T01:02:49.852047Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:49.852047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Alex Kendall, Roberto Cipolla, Vijay Badrinarayanan","submitted_at":"2015-11-09T14:00:21Z","abstract_excerpt":"We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making. Our contribution is a practical system which is able to predict pixel-wise class labels with a measure of model uncertainty. We achieve this by Monte Carlo sampling with dropout at test time to generate a posterior distribution of pixel class labels. In addition, we show that modelling uncertainty improves segmentation performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02680","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1511.02680","created_at":"2026-05-18T01:02:49.852119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.02680v2","created_at":"2026-05-18T01:02:49.852119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02680","created_at":"2026-05-18T01:02:49.852119+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YMTT3XCRAXU","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YMTT3XCRAXU6DU5","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YMTT3XC","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2501.08083","citing_title":"Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2502.09269","citing_title":"Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19993","citing_title":"Algorithm and Hardware Co-Design for Efficient Complex-Valued Uncertainty Estimation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02380","citing_title":"UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD","json":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD.json","graph_json":"https://pith.science/api/pith-number/6YMTT3XCRAXU6DU5XJEKOSWICD/graph.json","events_json":"https://pith.science/api/pith-number/6YMTT3XCRAXU6DU5XJEKOSWICD/events.json","paper":"https://pith.science/paper/6YMTT3XC"},"agent_actions":{"view_html":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD","download_json":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD.json","view_paper":"https://pith.science/paper/6YMTT3XC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.02680&json=true","fetch_graph":"https://pith.science/api/pith-number/6YMTT3XCRAXU6DU5XJEKOSWICD/graph.json","fetch_events":"https://pith.science/api/pith-number/6YMTT3XCRAXU6DU5XJEKOSWICD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD/action/storage_attestation","attest_author":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD/action/author_attestation","sign_citation":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD/action/citation_signature","submit_replication":"https://pith.science/pith/6YMTT3XCRAXU6DU5XJEKOSWICD/action/replication_record"}},"created_at":"2026-05-18T01:02:49.852119+00:00","updated_at":"2026-05-18T01:02:49.852119+00:00"}